Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already flag destructiveHint=true and idempotentHint=false, and the description adds meaning beyond them: the command is auditable, it cannot complete or reopen a case, and a premature decision is latched until applicable (asynchronous behavior). It does not describe side effects on case state per command type, but the addition is substantive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four tight sentences, front-loaded with the core action, then constraints, then the checks_go special case. The middle sentence is dense and reads slightly run-on, but nothing is padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, non-idempotent mutation with no output schema and 0% schema coverage, the description leaves notable gaps: what a successful submission returns, whether idempotency_key prevents duplicate commands, and what permissions or preconditions apply. It covers enough to start but not enough to call confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the load. It explains payload.decision values and the optional rationale for checks_go, and loosely maps the enum to concepts, but says nothing about case_id, trace_id, idempotency_key, or the payload shape for approve_fact/correct_fact/escalate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (submit an auditable intake-review command) and enumerates the allowed command families: review/correct facts, update evidence, escalate, checks_go. It also draws a hard boundary (cannot complete or reopen a case), which sharpens what the tool is not.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete operating guidance for the trickiest path: for checks_go supply payload.decision as go/not_now/withdraw and poll get_review_command, plus a warning that a decision sent before case start stays accepted until it applies. Missing is general guidance on when to choose this over sibling intake tools like submit_intake or answer_question.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.